hjkim

hojie11's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 3 papers 3 days ago

LayerComposer: Interactive Personalized T2I via Spatially-Aware Layered Canvas

Paper • 2510.20820 • Published 3 days ago • 7

HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives

Paper • 2510.20822 • Published 3 days ago • 32

Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall

Paper • 2510.19304 • Published 5 days ago • 22

upvoted 5 papers 4 days ago

OmniNWM: Omniscient Driving Navigation World Models

Paper • 2510.18313 • Published 6 days ago • 8

GigaBrain-0: A World Model-Powered Vision-Language-Action Model

Paper • 2510.19430 • Published 5 days ago • 37

Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing

Paper • 2510.19808 • Published 4 days ago • 21

Unified Reinforcement and Imitation Learning for Vision-Language Models

Paper • 2510.19307 • Published 5 days ago • 22

LightMem: Lightweight and Efficient Memory-Augmented Generation

Paper • 2510.18866 • Published 5 days ago • 101

upvoted a paper 5 days ago

World-in-World: World Models in a Closed-Loop World

Paper • 2510.18135 • Published 6 days ago • 80

upvoted 2 papers 6 days ago

RL makes MLLMs see better than SFT

Paper • 2510.16333 • Published 9 days ago • 43

ConsistEdit: Highly Consistent and Precise Training-free Visual Editing

Paper • 2510.17803 • Published 6 days ago • 12

upvoted 2 papers 7 days ago

OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM

Paper • 2510.15870 • Published 9 days ago • 73

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

Paper • 2510.15869 • Published 9 days ago • 40

upvoted 4 papers 10 days ago

WithAnyone: Towards Controllable and ID Consistent Image Generation

Paper • 2510.14975 • Published 10 days ago • 77

Less is More: Recursive Reasoning with Tiny Networks

Paper • 2510.04871 • Published 20 days ago • 446

DreamOmni2: Multimodal Instruction-based Editing and Generation

Paper • 2510.06679 • Published 19 days ago • 73

VIST3A: Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator

Paper • 2510.13454 • Published 12 days ago • 6

upvoted a paper 11 days ago

FlashWorld: High-quality 3D Scene Generation within Seconds

Paper • 2510.13678 • Published 11 days ago • 69

upvoted 2 papers 12 days ago

Detect Anything via Next Point Prediction

Paper • 2510.12798 • Published 12 days ago • 42

Advancing End-to-End Pixel Space Generative Modeling via Self-supervised Pre-training

Paper • 2510.12586 • Published 12 days ago • 106